Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express the act of "setting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĤãĤĬ
    -0.18
    ร
    -0.17
    dden
    -0.16
    eric
    -0.15
    acht
    -0.15
    uments
    -0.15
    inz
    -0.15
    /student
    -0.14
    Ùĩ
    -0.14
    nemonic
    -0.14
    POSITIVE LOGITS
    tle
    0.21
    tlement
    0.20
    elah
    0.19
    ted
    0.18
    tement
    0.17
    iap
    0.17
    ched
    0.16
    TL
    0.16
    ters
    0.15
    sockopt
    0.15
    Act Density 0.122%

    No Known Activations